Direct Prediction of the Toxic Gas Diffusion Rule in a Real Environment Based on LSTM.

Fei Qian,Chao Ding,Jun Li,Xianfu Chen,Jian Wang,Li Chen

doi:10.3390/ijerph16122133

Abstract

Predicting the diffusion rule of toxic gas plays a distinctly important role in emergency capability assessment and rescue work. Among diffusion prediction models, the traditional artificial neural network has exhibited excellent performance not only in prediction accuracy but also in calculation time. Nevertheless, with the continuous development of deep learning and data science, some new prediction models based on deep learning algorithms have been shown to be more advantageous because their structure can better discover internal laws and external connections between input data and output data. The long short-term memory (LSTM) network is a kind of deep learning neural network that has demonstrated outstanding achievements in many prediction fields. This paper applies the LSTM network directly to the prediction of toxic gas diffusion and uses the Project Prairie Grass dataset to conduct experiments. Compared with the Gaussian diffusion model, support vector machine (SVM) model, and back propagation (BP) network model, the LSTM model of deep learning has higher prediction accuracy (especially for the prediction at the point of high concentration values) while avoiding the occurrence of negative concentration values and overfitting problems found in traditional artificial neural network models.

Highlights

In recent years, toxic gas leaks caused by chemical plant explosion accidents, forest fires, etc., have frequently occurred in various countries, seriously affecting people’s lives, health, and property.In 2019, chemical plant explosions in Yancheng, China and Houston, USA and forest fires in Sichuan, China all caused a large area of toxic gas leakage and diffusion, which harmed people’s health and greatly hindered rescue work
Both the back propagation (BP) model and the long short-term memory network (LSTM) model use the average performance of 10 experiments
The LSTM deep learning algorithm was applied to the prediction of toxic gas diffusion in a real environment with the aim to make an accurate pre-judgment on the diffusion rule of toxic gases

Summary

Introduction

Toxic gas leaks caused by chemical plant explosion accidents, forest fires, etc., have frequently occurred in various countries, seriously affecting people’s lives, health, and property. In 2019, chemical plant explosions in Yancheng, China and Houston, USA and forest fires in Sichuan, China all caused a large area of toxic gas leakage and diffusion, which harmed people’s health and greatly hindered rescue work. Typical examples of mathematical calculations include Gaussian diffusion models and computational fluid dynamics (CFD) models [1]. The Gaussian diffusion model uses plain mathematical formulas that can be calculated and cost less time, but it only applies to describing unobstructed gas flow over flat terrain and its predictions in complex environments are often unreliable [2]. There is a big drawback in that it takes too long for CFD to

Methods

Results

Conclusion